Add new SentenceTransformer model.

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,575 @@
+---
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+datasets:
+- sentence-transformers/quora-duplicates
+language:
+- en
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+- cosine_accuracy_threshold
+- cosine_f1
+- cosine_f1_threshold
+- cosine_precision
+- cosine_recall
+- cosine_ap
+- dot_accuracy
+- dot_accuracy_threshold
+- dot_f1
+- dot_f1_threshold
+- dot_precision
+- dot_recall
+- dot_ap
+- manhattan_accuracy
+- manhattan_accuracy_threshold
+- manhattan_f1
+- manhattan_f1_threshold
+- manhattan_precision
+- manhattan_recall
+- manhattan_ap
+- euclidean_accuracy
+- euclidean_accuracy_threshold
+- euclidean_f1
+- euclidean_f1_threshold
+- euclidean_precision
+- euclidean_recall
+- euclidean_ap
+- max_accuracy
+- max_accuracy_threshold
+- max_f1
+- max_f1_threshold
+- max_precision
+- max_recall
+- max_ap
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:323432
+- loss:OnlineContrastiveLoss
+widget:
+- source_sentence: How do I have a successful career in animation industry with all
+    distance mode of education (from schooling)?
+  sentences:
+  - The LINE app is blocked in China. I bought a VPN, but it's still not working.
+    Can someone help me?
+  - What is independent?
+  - How do I find all distance education schools in any city?
+- source_sentence: How can I get the funding for my startup without revealing my idea?
+  sentences:
+  - How has demonetization affected big business people like Mukesh Ambani?
+  - How should I go about getting funding for my idea?
+  - What are the advantages and disadvantages of studying an MBBS in China?
+- source_sentence: I am an okay looking young women but I am always feeling ugly since
+    I'm not extremely beautiful. How can I stop those thoughts?
+  sentences:
+  - Whenever I think about my failures in life, I always feel that I lack some qualities.
+    But which are those qualities, I am not able to find out. How can I find which
+    qualities I lack?
+  - What songs make you cry?
+  - What does histrionic personality disorder feel like physically to you?
+- source_sentence: What do you think of Prime Minister Narendra Modi's decision to
+    introduce new INR 500 and INR 2000 currency notes?
+  sentences:
+  - What do you think of the decision by the Indian Government to replace 1000 notes
+    with 2000 notes?
+  - How do you find volume from density and mass?
+  - What are the consequences of having a blood sugar level over 300?
+- source_sentence: Why do complementary angles have to be adjacent?
+  sentences:
+  - What is an AEG airsoft gun?
+  - How can I get rid of my bad habits?
+  - Can two adjacent angles be complementary?
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+  results:
+  - task:
+      type: binary-classification
+      name: Binary Classification
+    dataset:
+      name: Unknown
+      type: unknown
+    metrics:
+    - type: cosine_accuracy
+      value: 0.8683618194860125
+      name: Cosine Accuracy
+    - type: cosine_accuracy_threshold
+      value: 0.7981455326080322
+      name: Cosine Accuracy Threshold
+    - type: cosine_f1
+      value: 0.8292439905343131
+      name: Cosine F1
+    - type: cosine_f1_threshold
+      value: 0.7598952651023865
+      name: Cosine F1 Threshold
+    - type: cosine_precision
+      value: 0.7746589487768696
+      name: Cosine Precision
+    - type: cosine_recall
+      value: 0.8921046460992195
+      name: Cosine Recall
+    - type: cosine_ap
+      value: 0.8822291610822541
+      name: Cosine Ap
+    - type: dot_accuracy
+      value: 0.8359964382003018
+      name: Dot Accuracy
+    - type: dot_accuracy_threshold
+      value: 17.112058639526367
+      name: Dot Accuracy Threshold
+    - type: dot_f1
+      value: 0.7914425390403506
+      name: Dot F1
+    - type: dot_f1_threshold
+      value: 16.083341598510742
+      name: Dot F1 Threshold
+    - type: dot_precision
+      value: 0.7294350282485875
+      name: Dot Precision
+    - type: dot_recall
+      value: 0.8649716946370549
+      name: Dot Recall
+    - type: dot_ap
+      value: 0.8438654629805356
+      name: Dot Ap
+    - type: manhattan_accuracy
+      value: 0.8568230725469341
+      name: Manhattan Accuracy
+    - type: manhattan_accuracy_threshold
+      value: 46.94310760498047
+      name: Manhattan Accuracy Threshold
+    - type: manhattan_f1
+      value: 0.8144082547946494
+      name: Manhattan F1
+    - type: manhattan_f1_threshold
+      value: 50.51482391357422
+      name: Manhattan F1 Threshold
+    - type: manhattan_precision
+      value: 0.7656268427880646
+      name: Manhattan Precision
+    - type: manhattan_recall
+      value: 0.8698288279234918
+      name: Manhattan Recall
+    - type: manhattan_ap
+      value: 0.8636170591577621
+      name: Manhattan Ap
+    - type: euclidean_accuracy
+      value: 0.8568849093472507
+      name: Euclidean Accuracy
+    - type: euclidean_accuracy_threshold
+      value: 3.0017127990722656
+      name: Euclidean Accuracy Threshold
+    - type: euclidean_f1
+      value: 0.8143016129285076
+      name: Euclidean F1
+    - type: euclidean_f1_threshold
+      value: 3.2429399490356445
+      name: Euclidean F1 Threshold
+    - type: euclidean_precision
+      value: 0.7652309686542541
+      name: Euclidean Precision
+    - type: euclidean_recall
+      value: 0.8700968076910194
+      name: Euclidean Recall
+    - type: euclidean_ap
+      value: 0.8637642883474006
+      name: Euclidean Ap
+    - type: max_accuracy
+      value: 0.8683618194860125
+      name: Max Accuracy
+    - type: max_accuracy_threshold
+      value: 46.94310760498047
+      name: Max Accuracy Threshold
+    - type: max_f1
+      value: 0.8292439905343131
+      name: Max F1
+    - type: max_f1_threshold
+      value: 50.51482391357422
+      name: Max F1 Threshold
+    - type: max_precision
+      value: 0.7746589487768696
+      name: Max Precision
+    - type: max_recall
+      value: 0.8921046460992195
+      name: Max Recall
+    - type: max_ap
+      value: 0.8822291610822541
+      name: Max Ap
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) on the [sentence-transformers/quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) <!-- at revision bf3bf13ab40c3157080a7ab344c831b9ad18b5eb -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 384 tokens
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [sentence-transformers/quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates)
+- **Language:** en
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("DashReza7/paraphrase-multilingual-MiniLM-L12-v2_QuoraDuplicateDetection_FINETUNED")
+# Run inference
+sentences = [
+    'Why do complementary angles have to be adjacent?',
+    'Can two adjacent angles be complementary?',
+    'How can I get rid of my bad habits?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 384]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Binary Classification
+
+* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
+
+| Metric                       | Value      |
+|:-----------------------------|:-----------|
+| cosine_accuracy              | 0.8684     |
+| cosine_accuracy_threshold    | 0.7981     |
+| cosine_f1                    | 0.8292     |
+| cosine_f1_threshold          | 0.7599     |
+| cosine_precision             | 0.7747     |
+| cosine_recall                | 0.8921     |
+| cosine_ap                    | 0.8822     |
+| dot_accuracy                 | 0.836      |
+| dot_accuracy_threshold       | 17.1121    |
+| dot_f1                       | 0.7914     |
+| dot_f1_threshold             | 16.0833    |
+| dot_precision                | 0.7294     |
+| dot_recall                   | 0.865      |
+| dot_ap                       | 0.8439     |
+| manhattan_accuracy           | 0.8568     |
+| manhattan_accuracy_threshold | 46.9431    |
+| manhattan_f1                 | 0.8144     |
+| manhattan_f1_threshold       | 50.5148    |
+| manhattan_precision          | 0.7656     |
+| manhattan_recall             | 0.8698     |
+| manhattan_ap                 | 0.8636     |
+| euclidean_accuracy           | 0.8569     |
+| euclidean_accuracy_threshold | 3.0017     |
+| euclidean_f1                 | 0.8143     |
+| euclidean_f1_threshold       | 3.2429     |
+| euclidean_precision          | 0.7652     |
+| euclidean_recall             | 0.8701     |
+| euclidean_ap                 | 0.8638     |
+| max_accuracy                 | 0.8684     |
+| max_accuracy_threshold       | 46.9431    |
+| max_f1                       | 0.8292     |
+| max_f1_threshold             | 50.5148    |
+| max_precision                | 0.7747     |
+| max_recall                   | 0.8921     |
+| **max_ap**                   | **0.8822** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### sentence-transformers/quora-duplicates
+
+* Dataset: [sentence-transformers/quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 323,432 training samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                        | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                           | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 16.39 tokens</li><li>max: 80 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 16.2 tokens</li><li>max: 71 tokens</li></ul> | <ul><li>0: ~62.10%</li><li>1: ~37.90%</li></ul> |
+* Samples:
+  | sentence1                                                                  | sentence2                                                              | label          |
+  |:---------------------------------------------------------------------------|:-----------------------------------------------------------------------|:---------------|
+  | <code>Which are the best compilers for C language (for Windows 10)?</code> | <code>Which is the best open source C/C++ compiler for Windows?</code> | <code>0</code> |
+  | <code>How much does YouTube pay per 1000 views in India?</code>            | <code>How much does youtube pay per 1000 views?</code>                 | <code>0</code> |
+  | <code>What parts do I need to build my own PC?</code>                      | <code>I want to build a new computer. What parts do I need?</code>     | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Evaluation Dataset
+
+#### sentence-transformers/quora-duplicates
+
+* Dataset: [sentence-transformers/quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb)
+* Size: 80,858 evaluation samples
+* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence1                                                                         | sentence2                                                                          | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                             | int                                             |
+  | details | <ul><li>min: 6 tokens</li><li>mean: 16.48 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.76 tokens</li><li>max: 101 tokens</li></ul> | <ul><li>0: ~63.90%</li><li>1: ~36.10%</li></ul> |
+* Samples:
+  | sentence1                                                                | sentence2                                                                    | label          |
+  |:-------------------------------------------------------------------------|:-----------------------------------------------------------------------------|:---------------|
+  | <code>How many stories got busted on Quora while being anonymous?</code> | <code>Can what I say on Quora anonymously be used against me legally?</code> | <code>0</code> |
+  | <code>What are innovative mechanical component designs?</code>           | <code>What is the Innovation design?</code>                                  | <code>0</code> |
+  | <code>What is the best way to learn phrasal verbs?</code>                | <code>Why should I learn phrasal verbs?</code>                               | <code>1</code> |
+* Loss: [<code>OnlineContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#onlinecontrastiveloss)
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `fp16`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 256
+- `per_device_eval_batch_size`: 256
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | loss   | max_ap |
+|:------:|:----:|:-------------:|:------:|:------:|
+| 0.0791 | 100  | -             | 8.0607 | 0.8164 |
+| 0.1582 | 200  | -             | 7.3012 | 0.8445 |
+| 0.2373 | 300  | -             | 6.9626 | 0.8582 |
+| 0.3165 | 400  | -             | 6.7901 | 0.8639 |
+| 0.3956 | 500  | 7.5229        | 6.6498 | 0.8694 |
+| 0.4747 | 600  | -             | 6.5315 | 0.8736 |
+| 0.5538 | 700  | -             | 6.4686 | 0.8766 |
+| 0.6329 | 800  | -             | 6.4027 | 0.8787 |
+| 0.7120 | 900  | -             | 6.3108 | 0.8797 |
+| 0.7911 | 1000 | 6.4636        | 6.2862 | 0.8812 |
+| 0.8703 | 1100 | -             | 6.2449 | 0.8818 |
+| 0.9494 | 1200 | -             | 6.2344 | 0.8822 |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.0.1
+- Transformers: 4.42.4
+- PyTorch: 2.3.1+cu121
+- Accelerate: 0.32.1
+- Datasets: 2.21.0
+- Tokenizers: 0.19.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.0.1",
+    "transformers": "4.42.4",
+    "pytorch": "2.3.1+cu121"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f57166974b54b26554feaa6064b011aad8e79452ccce4f3357fb8020a11203e
+size 470637416

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260